df['arrival_delay_in_minutes'] = df['arrival_delay_in_minutes'].fillna(df['arrival_delay_in_minutes'].median())
The dataset has slightly more number of female passengers than male passengers.
The proportion of loyal customer are much more than disloyal customer.
More number of passengers are going for business travel than personal travel.
There are 48%, 7% and 45% customers travelling through business, Economy plus and Economic class respectively.
The proportion of satisfied people are less than the neutral or dissatisfied customers.
The average rating is 2 or 3 with maximum people have given rating 2 to inflight_wifi_service. This implies inflight_wifi_service has to be improved.
Maximum number of customers have given rating 4 to departure_arrival_time_convenient. This implies people are satisfied with departure_arrival_time.
The average rating is 2 or 3 with maximum people have given rating 3 to ease_of_online_booking. This implies quite decent figures.
The average rating is 3 or 4 with maximum people have given rating 3 to gate_location. This implies people are satisfied with gate_location.
More number of people have given 4 & 5 ratings, However ratings are distributed across 2,3,5 almost equaually with 4 getting the highest count. The ratings are quite varying.
Maximum number of customers have given rating 4 to online_boarding which is quite good.
More number of people have given rating 4 to seat_comfort followed by 5. Maximum number of people are comfortable with seat.
More number of people have given rating 4 to inflight_entertainment followed by 5. Maximum number of people are satisfied with inflight_entertainment.
More number of people have given rating 4 to onbord_service followed by 5. Maximum number of people are satisfied with onboard_service.
More number of people have given rating 4 to leg_room_service followed by 5. Maximum number of people are satisfied with leg_room_service.
More number of people have given rating 4 to baggage_handling followed by 5. Maximum number of people are satisfied with baggage_handling.
More number of people have given rating 4 to checkin_service followed by 3. Maximum number of people are quite satisfied with checkin_service, However It can be slightly improved.
Maximum number of people have given rating 4 to inflight_service followed by 5. Maximum number of people are satisfied with inflight_service.
More number of people have given rating 4 to cleanliness followed by 3. Maximum number of people are quite satisfied with cleanliness.
More number of male and female are neutral or dissatisfied.
A large number of loyal customers are neutral or dissatisfied. Maximum disloyal customers are neutral or dissatified only.
More people who travel for personal reasons are neutral or dissatisfied. Business purpose travellers are usually satisfied. It might be because of the class they are travelling.
Here we can see mostly people who travel for business purpose choose business class and hence are more satisfied.
People travelling with business class are usually satisfied. People travelling through Eco plus and Eco class are usually neutral or dissatisfied.
More number of customers are neutal or dissatisfied compared to customers who are satisfied.
More customers who have given 2 &3 ratings are usually dissatified. Inflight wigfi service has to be improved.
Here we can see people who have given 4 and 5 ratings are more neutral or dissatisfied. So this is not an important parameter for measuring satisfaction.
Customers who have given 3 & 4 ratings and neutral or dissatisfied. Only those who have given 5 ratings are satisfied. There can be some technical glitches which can be improved for those who have given 3 rating.
Here we can see people who have given 3 and 4 ratings are more neutral or dissatisfied. So this can be considered as not a very important parameter for measuring satisfaction.
Improving food and drinks can contribute to satisfaction as can be clearly seen from the chart.
Customer satisfaction is increasing with online boarding.
Customer satisfaction is increasing with seat comfort.
Customer satisfaction is increasing with inflight entertainment.
Customer satisfaction is increasing with onboard service.
Customer satisfaction is increasing with leg room service.
This plot shows slight imbalance. Satisfaction is increasing with baggage_handling. Although other parameters steer satisfaction even after 4 rating to baggage handling.
This plot shows that satisfaction is increasing with checkin service.
Satisfaction is increasing with inflight_service.
Satisfaction is increasing with cleanliness.
Most people in less distance flights are neutral or dissatisfied. More focus should be given here for increasing satisfaction.
There are few outliers of inflight_wifi_service for neutral or dissatisfied section of satisfaction. People are usually dissatisfied when wifi service is not good.
The mean age of customers who are satisfied is slightly more than those who are neutral or dissatisfied.
The mean age of departure_arrival_time_convenient for both class of satisfaction are equal.
The mean rating of ease_of_online_booking is more for satisfied people than people who are neutral or dissatisfied. There are few outliers where people are neutral or dissatisfied.
The mean age of gate_location for both class of satisfaction are equal.
The mean rating of food_and_drink is more for satisfied people than people who are neutral or dissatisfied.
The mean rating of online_boarding is more for satisfied people than people who are neutral or dissatisfied. There are outliers in the data.
The mean rating of seat_comfort is more for satisfied people than people who are neutral or dissatisfied. There are outliers in the data where people are satisfied.
The mean rating of inflight_entertainment is more for satisfied people than people who are neutral or dissatisfied. There are outliers in the data where people are satisfied.
The mean rating of onboard_service is more for satisfied people than people who are neutral or dissatisfied.
The mean rating of leg room service is more for satisfied people than people who are neutral or dissatisfied.
The mean rating of baggage handling is more for satisfied people than people who are neutral or dissatisfied. There are outliers in the data.
The mean rating of checkin service is more for satisfied people than people who are neutral or dissatisfied.
The mean rating inflight service is more for satisfied people than people who are neutral or dissatisfied. There are outliers in the data.
The mean rating of cleanliness is more for satisfied people than people who are neutral or dissatisfied.
PREPROCESSING FOR THE MODEL We want to predict the passenger satisfaction.